Training in progress epoch 2

README.md

@@ -14,13 +14,13 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.5667
-- Train End Logits Accuracy: 0.6029
-- Train Start Logits Accuracy: 0.5472
+- Train Loss: 1.4159
+- Train End Logits Accuracy: 0.6381
+- Train Start Logits Accuracy: 0.5826
 - Validation Loss: 1.5331
 - Validation End Logits Accuracy: 0.6169
 - Validation Start Logits Accuracy: 0.5583
-- Epoch: 1
+- Epoch: 2
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
 | 2.3671     | 0.4386                    | 0.3832                      | 1.6448          | 0.5845                         | 0.5326                           | 0     |
 | 1.5667     | 0.6029                    | 0.5472                      | 1.5331          | 0.6169                         | 0.5583                           | 1     |
+| 1.4159     | 0.6381                    | 0.5826                      | 1.5331          | 0.6169                         | 0.5583                           | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8486b32b7a847ba109d2572fa3602480c6f6725a250e2044cb29dbc3a1ac2cf6
+oid sha256:66f274eb03307956cd38ebf08f02066bf44a1a51b9716db294cc63986a47f6e1
 size 265583688